
# !pip install git+https://github.com/alberanid/imdbpy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask


# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")


nltk.download('all')

[nltk_data] Downloading collection 'all'
[nltk_data]    | 
[nltk_data]    | Downloading package abc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package abc is already up-to-date!
[nltk_data]    | Downloading package alpino to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package alpino is already up-to-date!
[nltk_data]    | Downloading package biocreative_ppi to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package biocreative_ppi is already up-to-date!
[nltk_data]    | Downloading package brown to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown is already up-to-date!
[nltk_data]    | Downloading package brown_tei to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown_tei is already up-to-date!
[nltk_data]    | Downloading package cess_cat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_cat is already up-to-date!
[nltk_data]    | Downloading package cess_esp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_esp is already up-to-date!
[nltk_data]    | Downloading package chat80 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package chat80 is already up-to-date!
[nltk_data]    | Downloading package city_database to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package city_database is already up-to-date!
[nltk_data]    | Downloading package cmudict to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cmudict is already up-to-date!
[nltk_data]    | Downloading package comparative_sentences to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comparative_sentences is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package comtrans to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comtrans is already up-to-date!
[nltk_data]    | Downloading package conll2000 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2000 is already up-to-date!
[nltk_data]    | Downloading package conll2002 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2002 is already up-to-date!
[nltk_data]    | Downloading package conll2007 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2007 is already up-to-date!
[nltk_data]    | Downloading package crubadan to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package crubadan is already up-to-date!
[nltk_data]    | Downloading package dependency_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dependency_treebank is already up-to-date!
[nltk_data]    | Downloading package dolch to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dolch is already up-to-date!
[nltk_data]    | Downloading package europarl_raw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package europarl_raw is already up-to-date!
[nltk_data]    | Downloading package floresta to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package floresta is already up-to-date!
[nltk_data]    | Downloading package framenet_v15 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v15 is already up-to-date!
[nltk_data]    | Downloading package framenet_v17 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v17 is already up-to-date!
[nltk_data]    | Downloading package gazetteers to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gazetteers is already up-to-date!
[nltk_data]    | Downloading package genesis to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package genesis is already up-to-date!
[nltk_data]    | Downloading package gutenberg to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gutenberg is already up-to-date!
[nltk_data]    | Downloading package ieer to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ieer is already up-to-date!
[nltk_data]    | Downloading package inaugural to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package inaugural is already up-to-date!
[nltk_data]    | Downloading package indian to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package indian is already up-to-date!
[nltk_data]    | Downloading package jeita to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package jeita is already up-to-date!
[nltk_data]    | Downloading package kimmo to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package kimmo is already up-to-date!
[nltk_data]    | Downloading package knbc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package knbc is already up-to-date!
[nltk_data]    | Downloading package lin_thesaurus to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package lin_thesaurus is already up-to-date!
[nltk_data]    | Downloading package mac_morpho to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mac_morpho is already up-to-date!
[nltk_data]    | Downloading package machado to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package machado is already up-to-date!
[nltk_data]    | Downloading package masc_tagged to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package masc_tagged is already up-to-date!
[nltk_data]    | Downloading package moses_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package moses_sample is already up-to-date!
[nltk_data]    | Downloading package movie_reviews to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package movie_reviews is already up-to-date!
[nltk_data]    | Downloading package names to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package names is already up-to-date!
[nltk_data]    | Downloading package nombank.1.0 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nombank.1.0 is already up-to-date!
[nltk_data]    | Downloading package nps_chat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nps_chat is already up-to-date!
[nltk_data]    | Downloading package omw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package omw is already up-to-date!
[nltk_data]    | Downloading package opinion_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package opinion_lexicon is already up-to-date!
[nltk_data]    | Downloading package paradigms to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package paradigms is already up-to-date!
[nltk_data]    | Downloading package pil to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pil is already up-to-date!
[nltk_data]    | Downloading package pl196x to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pl196x is already up-to-date!
[nltk_data]    | Downloading package ppattach to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ppattach is already up-to-date!
[nltk_data]    | Downloading package problem_reports to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package problem_reports is already up-to-date!
[nltk_data]    | Downloading package propbank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package propbank is already up-to-date!
[nltk_data]    | Downloading package ptb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ptb is already up-to-date!
[nltk_data]    | Downloading package product_reviews_1 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_1 is already up-to-date!
[nltk_data]    | Downloading package product_reviews_2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_2 is already up-to-date!
[nltk_data]    | Downloading package pros_cons to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pros_cons is already up-to-date!
[nltk_data]    | Downloading package qc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package qc is already up-to-date!
[nltk_data]    | Downloading package reuters to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package reuters is already up-to-date!
[nltk_data]    | Downloading package rte to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rte is already up-to-date!
[nltk_data]    | Downloading package semcor to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package semcor is already up-to-date!
[nltk_data]    | Downloading package senseval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package senseval is already up-to-date!
[nltk_data]    | Downloading package sentiwordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentiwordnet is already up-to-date!
[nltk_data]    | Downloading package sentence_polarity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentence_polarity is already up-to-date!
[nltk_data]    | Downloading package shakespeare to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package shakespeare is already up-to-date!
[nltk_data]    | Downloading package sinica_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sinica_treebank is already up-to-date!
[nltk_data]    | Downloading package smultron to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package smultron is already up-to-date!
[nltk_data]    | Downloading package state_union to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package state_union is already up-to-date!
[nltk_data]    | Downloading package stopwords to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package stopwords is already up-to-date!
[nltk_data]    | Downloading package subjectivity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package subjectivity is already up-to-date!
[nltk_data]    | Downloading package swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package swadesh is already up-to-date!
[nltk_data]    | Downloading package switchboard to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package switchboard is already up-to-date!
[nltk_data]    | Downloading package timit to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package timit is already up-to-date!
[nltk_data]    | Downloading package toolbox to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package toolbox is already up-to-date!
[nltk_data]    | Downloading package treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package treebank is already up-to-date!
[nltk_data]    | Downloading package twitter_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package twitter_samples is already up-to-date!
[nltk_data]    | Downloading package udhr to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr is already up-to-date!
[nltk_data]    | Downloading package udhr2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr2 is already up-to-date!
[nltk_data]    | Downloading package unicode_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package unicode_samples is already up-to-date!
[nltk_data]    | Downloading package universal_treebanks_v20 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_treebanks_v20 is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package verbnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet is already up-to-date!
[nltk_data]    | Downloading package verbnet3 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet3 is already up-to-date!
[nltk_data]    | Downloading package webtext to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package webtext is already up-to-date!
[nltk_data]    | Downloading package wordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet is already up-to-date!
[nltk_data]    | Downloading package wordnet_ic to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet_ic is already up-to-date!
[nltk_data]    | Downloading package words to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package words is already up-to-date!
[nltk_data]    | Downloading package ycoe to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ycoe is already up-to-date!
[nltk_data]    | Downloading package rslp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rslp is already up-to-date!
[nltk_data]    | Downloading package maxent_treebank_pos_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_treebank_pos_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package universal_tagset to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_tagset is already up-to-date!
[nltk_data]    | Downloading package maxent_ne_chunker to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_ne_chunker is already up-to-date!
[nltk_data]    | Downloading package punkt to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package punkt is already up-to-date!
[nltk_data]    | Downloading package book_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package book_grammars is already up-to-date!
[nltk_data]    | Downloading package sample_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sample_grammars is already up-to-date!
[nltk_data]    | Downloading package spanish_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package spanish_grammars is already up-to-date!
[nltk_data]    | Downloading package basque_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package basque_grammars is already up-to-date!
[nltk_data]    | Downloading package large_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package large_grammars is already up-to-date!
[nltk_data]    | Downloading package tagsets to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package tagsets is already up-to-date!
[nltk_data]    | Downloading package snowball_data to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package snowball_data is already up-to-date!
[nltk_data]    | Downloading package bllip_wsj_no_aux to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package bllip_wsj_no_aux is already up-to-date!
[nltk_data]    | Downloading package word2vec_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package word2vec_sample is already up-to-date!
[nltk_data]    | Downloading package panlex_swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package panlex_swadesh is already up-to-date!
[nltk_data]    | Downloading package mte_teip5 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mte_teip5 is already up-to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger_ru to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger_ru is already
[nltk_data]    |       up-to-date!
[nltk_data]    | Downloading package perluniprops to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package perluniprops is already up-to-date!
[nltk_data]    | Downloading package nonbreaking_prefixes to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nonbreaking_prefixes is already up-to-date!
[nltk_data]    | Downloading package vader_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package vader_lexicon is already up-to-date!
[nltk_data]    | Downloading package porter_test to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package porter_test is already up-to-date!
[nltk_data]    | Downloading package wmt15_eval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wmt15_eval is already up-to-date!
[nltk_data]    | Downloading package mwa_ppdb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mwa_ppdb is already up-to-date!
[nltk_data]    | 
[nltk_data]  Done downloading collection all

True


# path = '/content/drive/MyDrive/Files/'

path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
 
df_movies = pd.read_csv(path + 'ottmovies.csv')
 
df_movies.head()


# profile = ProfileReport(df_movies)
# profile


def data_investigate(df):
    print('No of Rows : ', df.shape[0])
    print('No of Coloums : ', df.shape[1])
    print('**'*25)
    print('Colums Names : \n', df.columns)
    print('**'*25)
    print('Datatype of Columns : \n', df.dtypes)
    print('**'*25)
    print('Missing Values : ')
    c = df.isnull().sum()
    c = c[c > 0]
    print(c)
    print('**'*25)
    print('Missing vaules %age wise :\n')
    print((100*(df.isnull().sum()/len(df.index))))
    print('**'*25)
    print('Pictorial Representation : ')
    plt.figure(figsize = (10, 10))
    sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
    plt.show()


data_investigate(df_movies)

No of Rows :  16923
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb               float64
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime            float64
Kind                object
Seasons            float64
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
dtype: object
**************************************************
Missing Values : 
Age                 8457
IMDb                 328
Rotten Tomatoes    10437
Directors            357
Cast                 648
Genres               234
Country              303
Language             437
Plotline            4958
Runtime              382
Seasons            16923
dtype: int64
**************************************************
Missing vaules %age wise :

ID                   0.000000
Title                0.000000
Year                 0.000000
Age                 49.973409
IMDb                 1.938191
Rotten Tomatoes     61.673462
Directors            2.109555
Cast                 3.829108
Genres               1.382734
Country              1.790463
Language             2.582284
Plotline            29.297406
Runtime              2.257283
Kind                 0.000000
Seasons            100.000000
Netflix              0.000000
Hulu                 0.000000
Prime Video          0.000000
Disney+              0.000000
Type                 0.000000
dtype: float64
**************************************************
Pictorial Representation :


# ID
# df_movies = df_movies.drop(['ID'], axis = 1)
 
# Age
df_movies.loc[df_movies['Age'].isnull() & df_movies['Disney+'] == 1, "Age"] = '13'
# df_movies.fillna({'Age' : 18}, inplace = True)
df_movies.fillna({'Age' : 'NR'}, inplace = True)
df_movies['Age'].replace({'all': '0'}, inplace = True)
df_movies['Age'].replace({'7+': '7'}, inplace = True)
df_movies['Age'].replace({'13+': '13'}, inplace = True)
df_movies['Age'].replace({'16+': '16'}, inplace = True)
df_movies['Age'].replace({'18+': '18'}, inplace = True)
# df_movies['Age'] = df_movies['Age'].astype(int)
 
# IMDb
# df_movies.fillna({'IMDb' : df_movies['IMDb'].mean()}, inplace = True)
# df_movies.fillna({'IMDb' : df_movies['IMDb'].median()}, inplace = True)
df_movies.fillna({'IMDb' : "NA"}, inplace = True)
 
# Rotten Tomatoes
df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'][df_movies['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'][df_movies['Rotten Tomatoes'].notnull()].astype(int)
# df_movies.fillna({'Rotten Tomatoes' : df_movies['Rotten Tomatoes'].mean()}, inplace = True)
# df_movies.fillna({'Rotten Tomatoes' : df_movies['Rotten Tomatoes'].median()}, inplace = True)
# df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'].astype(int)
df_movies.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
 
# Directors
# df_movies = df_movies.drop(['Directors'], axis = 1)
df_movies.fillna({'Directors' : "NA"}, inplace = True)
 
# Cast
df_movies.fillna({'Cast' : "NA"}, inplace = True)
 
# Genres
df_movies.fillna({'Genres': "NA"}, inplace = True)
 
# Country
df_movies.fillna({'Country': "NA"}, inplace = True)
 
# Language
df_movies.fillna({'Language': "NA"}, inplace = True)
 
# Plotline
df_movies.fillna({'Plotline': "NA"}, inplace = True)
 
# Runtime
# df_movies.fillna({'Runtime' : df_movies['Runtime'].mean()}, inplace = True)
# df_movies['Runtime'] = df_movies['Runtime'].astype(int)
df_movies.fillna({'Runtime' : "NA"}, inplace = True)
 
# Kind
# df_movies.fillna({'Kind': "NA"}, inplace = True)
 
# Type
# df_movies.fillna({'Type': "NA"}, inplace = True)
# df_movies = df_movies.drop(['Type'], axis = 1)
 
# Seasons
# df_movies.fillna({'Seasons': 1}, inplace = True)
# df_movies.fillna({'Seasons': "NA"}, inplace = True)
df_movies = df_movies.drop(['Seasons'], axis = 1)
# df_movies['Seasons'] = df_movies['Seasons'].astype(int)
# df_movies.fillna({'Seasons' : df_movies['Seasons'].mean()}, inplace = True)
# df_movies['Seasons'] = df_movies['Seasons'].astype(int)
 
# Service Provider
df_movies['Service Provider'] = df_movies.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_movies.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)

# Removing Duplicate and Missing Entries
df_movies.dropna(how = 'any', inplace = True)
df_movies.drop_duplicates(inplace = True)


data_investigate(df_movies)

No of Rows :  16923
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
       'Service Provider'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb                object
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime             object
Kind                object
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
Service Provider    object
dtype: object
**************************************************
Missing Values : 
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :

ID                  0.0
Title               0.0
Year                0.0
Age                 0.0
IMDb                0.0
Rotten Tomatoes     0.0
Directors           0.0
Cast                0.0
Genres              0.0
Country             0.0
Language            0.0
Plotline            0.0
Runtime             0.0
Kind                0.0
Netflix             0.0
Hulu                0.0
Prime Video         0.0
Disney+             0.0
Type                0.0
Service Provider    0.0
dtype: float64
**************************************************
Pictorial Representation :


df_movies.head()


df_movies.describe()


df_movies.corr()


# df_movies.sort_values('Year', ascending = True)
# df_movies.sort_values('IMDb', ascending = False)


# df_movies.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_ottmovies.csv', index = False)
 
# path = '/content/drive/MyDrive/Files/'
 
# udf_movies = pd.read_csv(path + 'updated_ottmovies.csv')
 
# udf_movies


# df_netflix_movies = df_movies.loc[(df_movies['Netflix'] > 0)]
# df_hulu_movies = df_movies.loc[(df_movies['Hulu'] > 0)]
# df_prime_video_movies = df_movies.loc[(df_movies['Prime Video'] > 0)]
# df_disney_movies = df_movies.loc[(df_movies['Disney+'] > 0)]


df_netflix_only_movies = df_movies[(df_movies['Netflix'] == 1) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 0)]
df_hulu_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 1) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 0)]
df_prime_video_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 1 ) & (df_movies['Disney+'] == 0)]
df_disney_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 1)]


df_movies_countries = df_movies.copy()


df_movies_countries.drop(df_movies_countries.loc[df_movies_countries['Country'] == "NA"].index, inplace = True)
# df_movies_countries = df_movies_countries[df_movies_countries.Country != "NA"]
# df_movies_countries['Country'] = df_movies_countries['Country'].astype(str)


df_movies_count_countries = df_movies_countries.copy()


df_movies_country = df_movies_countries.copy()


# Create countries dict where key=name and value = number of countries
 
countries = {}
 
for i in df_movies_count_countries['Country'].dropna():
    if i != "NA":
        #print(i,len(i.split(',')))
        countries[i] = len(i.split(','))
    else:
        countries[i] = 0
    
# Add this information to our dataframe as a new column
 
df_movies_count_countries['Number of Countries'] = df_movies_count_countries['Country'].map(countries).astype(int)


df_movies_mixed_countries = df_movies_count_countries.copy()


# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_countries_movies = df_movies_count_countries.loc[df_movies_count_countries['Netflix'] == 1]
hulu_countries_movies = df_movies_count_countries.loc[df_movies_count_countries['Hulu'] == 1]
prime_video_countries_movies = df_movies_count_countries.loc[df_movies_count_countries['Prime Video'] == 1]
disney_countries_movies = df_movies_count_countries.loc[df_movies_count_countries['Disney+'] == 1]


plt.figure(figsize = (10, 10))
corr = df_movies_count_countries.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, alleast annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()

<Figure size 720x720 with 0 Axes>


df_countries_most_movies = df_movies_count_countries.sort_values(by = 'Number of Countries', ascending = False).reset_index()
df_countries_most_movies = df_countries_most_movies.drop(['index'], axis = 1)
# filter = (df_movies_count_countries['Number of Countries'] == (df_movies_count_countries['Number of Countries'].max()))
# df_countries_most_movies = df_movies_count_countries[filter]
 
# mostest_rated_movies = df_movies_count_countries.loc[df_movies_count_countries['Number of Countries'].idxmax()]
 
print('\nMovies with Highest Ever Number of Countries are : \n')
df_countries_most_movies.head(5)

Movies with Highest Ever Number of Countries are :


fig = px.bar(y = df_countries_most_movies['Title'][:15],
             x = df_countries_most_movies['Number of Countries'][:15], 
             color = df_countries_most_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Highest Number of Countries : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_countries_least_movies = df_movies_count_countries.sort_values(by = 'Number of Countries', ascending = True).reset_index()
df_countries_least_movies = df_countries_least_movies.drop(['index'], axis = 1)
# filter = (df_movies_count_countries['Number of Countries'] == (df_movies_count_countries['Number of Countries'].min()))
# df_countries_least_movies = df_movies_count_countries[filter]

print('\nMovies with Lowest Ever Number of Countries are : \n')
df_countries_least_movies.head(5)

Movies with Lowest Ever Number of Countries are :


fig = px.bar(y = df_countries_least_movies['Title'][:15],
             x = df_countries_least_movies['Number of Countries'][:15], 
             color = df_countries_least_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Lowest Number of Countries : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_movies_count_countries['Number of Countries'].unique().shape[0]}' unique Number of Countries s were Given, They were Like this,\n
      
      {df_movies_count_countries.sort_values(by = 'Number of Countries', ascending = False)['Number of Countries'].unique()}\n
 
      The Highest Number of Countries Ever Any Movie Got is '{df_countries_most_movies['Title'][0]}' : '{df_countries_most_movies['Number of Countries'].max()}'\n
 
      The Lowest Number of Countries Ever Any Movie Got is '{df_countries_least_movies['Title'][0]}' : '{df_countries_least_movies['Number of Countries'].min()}'\n
      ''')

      Total '16' unique Number of Countries s were Given, They were Like this,

      
      [27 20 19 18 15 11 10  9  8  7  6  5  4  3  2  1]

 
      The Highest Number of Countries Ever Any Movie Got is 'Somewhere Else Tomorrow' : '27'

 
      The Lowest Number of Countries Ever Any Movie Got is 'Citizen Architect: Samuel Mockbee and the Spirit of the Rural Studio' : '1'


netflix_countries_most_movies = df_countries_most_movies.loc[df_countries_most_movies['Netflix']==1].reset_index()
netflix_countries_most_movies = netflix_countries_most_movies.drop(['index'], axis = 1)
 
netflix_countries_least_movies = df_countries_least_movies.loc[df_countries_least_movies['Netflix']==1].reset_index()
netflix_countries_least_movies = netflix_countries_least_movies.drop(['index'], axis = 1)
 
netflix_countries_most_movies.head(5)


fig = px.bar(y = netflix_countries_most_movies['Title'][:15],
             x = netflix_countries_most_movies['Number of Countries'][:15], 
             color = netflix_countries_most_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Highest Number of Countries : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = netflix_countries_least_movies['Title'][:15],
             x = netflix_countries_least_movies['Number of Countries'][:15], 
             color = netflix_countries_least_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Lowest Number of Countries : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


hulu_countries_most_movies = df_countries_most_movies.loc[df_countries_most_movies['Hulu']==1].reset_index()
hulu_countries_most_movies = hulu_countries_most_movies.drop(['index'], axis = 1)
 
hulu_countries_least_movies = df_countries_least_movies.loc[df_countries_least_movies['Hulu']==1].reset_index()
hulu_countries_least_movies = hulu_countries_least_movies.drop(['index'], axis = 1)
 
hulu_countries_most_movies.head(5)


fig = px.bar(y = hulu_countries_most_movies['Title'][:15],
             x = hulu_countries_most_movies['Number of Countries'][:15], 
             color = hulu_countries_most_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Highest Number of Countries : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = hulu_countries_least_movies['Title'][:15],
             x = hulu_countries_least_movies['Number of Countries'][:15], 
             color = hulu_countries_least_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Lowest Number of Countries : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


prime_video_countries_most_movies = df_countries_most_movies.loc[df_countries_most_movies['Prime Video']==1].reset_index()
prime_video_countries_most_movies = prime_video_countries_most_movies.drop(['index'], axis = 1)
 
prime_video_countries_least_movies = df_countries_least_movies.loc[df_countries_least_movies['Prime Video']==1].reset_index()
prime_video_countries_least_movies = prime_video_countries_least_movies.drop(['index'], axis = 1)
 
prime_video_countries_most_movies.head(5)


fig = px.bar(y = prime_video_countries_most_movies['Title'][:15],
             x = prime_video_countries_most_movies['Number of Countries'][:15], 
             color = prime_video_countries_most_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Highest Number of Countries : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = prime_video_countries_least_movies['Title'][:15],
             x = prime_video_countries_least_movies['Number of Countries'][:15], 
             color = prime_video_countries_least_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Lowest Number of Countries : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


disney_countries_most_movies = df_countries_most_movies.loc[df_countries_most_movies['Disney+']==1].reset_index()
disney_countries_most_movies = disney_countries_most_movies.drop(['index'], axis = 1)
 
disney_countries_least_movies = df_countries_least_movies.loc[df_countries_least_movies['Disney+']==1].reset_index()
disney_countries_least_movies = disney_countries_least_movies.drop(['index'], axis = 1)
 
disney_countries_most_movies.head(5)


fig = px.bar(y = disney_countries_most_movies['Title'][:15],
             x = disney_countries_most_movies['Number of Countries'][:15], 
             color = disney_countries_most_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Highest Number of Countries : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = disney_countries_least_movies['Title'][:15],
             x = disney_countries_least_movies['Number of Countries'][:15], 
             color = disney_countries_least_movies['Number of Countries'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Countries'},
             title  = 'Movies with Lowest Number of Countries : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      The Movie with Highest Number of Countries Ever Got is '{df_countries_most_movies['Title'][0]}' : '{df_countries_most_movies['Number of Countries'].max()}'\n
      The Movie with Lowest Number of Countries Ever Got is '{df_countries_least_movies['Title'][0]}' : '{df_countries_least_movies['Number of Countries'].min()}'\n
      
      The Movie with Highest Number of Countries on 'Netflix' is '{netflix_countries_most_movies['Title'][0]}' : '{netflix_countries_most_movies['Number of Countries'].max()}'\n
      The Movie with Lowest Number of Countries on 'Netflix' is '{netflix_countries_least_movies['Title'][0]}' : '{netflix_countries_least_movies['Number of Countries'].min()}'\n
      
      The Movie with Highest Number of Countries on 'Hulu' is '{hulu_countries_most_movies['Title'][0]}' : '{hulu_countries_most_movies['Number of Countries'].max()}'\n
      The Movie with Lowest Number of Countries on 'Hulu' is '{hulu_countries_least_movies['Title'][0]}' : '{hulu_countries_least_movies['Number of Countries'].min()}'\n
      
      The Movie with Highest Number of Countries on 'Prime Video' is '{prime_video_countries_most_movies['Title'][0]}' : '{prime_video_countries_most_movies['Number of Countries'].max()}'\n
      The Movie with Lowest Number of Countries on 'Prime Video' is '{prime_video_countries_least_movies['Title'][0]}' : '{prime_video_countries_least_movies['Number of Countries'].min()}'\n
      
      The Movie with Highest Number of Countries on 'Disney+' is '{disney_countries_most_movies['Title'][0]}' : '{disney_countries_most_movies['Number of Countries'].max()}'\n
      The Movie with Lowest Number of Countries on 'Disney+' is '{disney_countries_least_movies['Title'][0]}' : '{disney_countries_least_movies['Number of Countries'].min()}'\n 
      ''')

      The Movie with Highest Number of Countries Ever Got is 'Somewhere Else Tomorrow' : '27'

      The Movie with Lowest Number of Countries Ever Got is 'Citizen Architect: Samuel Mockbee and the Spirit of the Rural Studio' : '1'

      
      The Movie with Highest Number of Countries on 'Netflix' is 'A Shaun the Sheep Movie: Farmageddon' : '10'

      The Movie with Lowest Number of Countries on 'Netflix' is 'My Sassy Girl' : '1'

      
      The Movie with Highest Number of Countries on 'Hulu' is 'Monos' : '10'

      The Movie with Lowest Number of Countries on 'Hulu' is 'Side Effects' : '1'

      
      The Movie with Highest Number of Countries on 'Prime Video' is 'Somewhere Else Tomorrow' : '27'

      The Movie with Lowest Number of Countries on 'Prime Video' is 'Citizen Architect: Samuel Mockbee and the Spirit of the Rural Studio' : '1'

      
      The Movie with Highest Number of Countries on 'Disney+' is 'Mulan II' : '15'

      The Movie with Lowest Number of Countries on 'Disney+' is 'The Swap' : '1'


print(f'''
      Accross All Platforms the Average Number of Countries is '{round(df_movies_count_countries['Number of Countries'].mean(), ndigits = 2)}'\n
      The Average Number of Countries on 'Netflix' is '{round(netflix_countries_movies['Number of Countries'].mean(), ndigits = 2)}'\n
      The Average Number of Countries on 'Hulu' is '{round(hulu_countries_movies['Number of Countries'].mean(), ndigits = 2)}'\n
      The Average Number of Countries on 'Prime Video' is '{round(prime_video_countries_movies['Number of Countries'].mean(), ndigits = 2)}'\n
      The Average Number of Countries on 'Disney+' is '{round(disney_countries_movies['Number of Countries'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Number of Countries is '1.29'

      The Average Number of Countries on 'Netflix' is '1.32'

      The Average Number of Countries on 'Hulu' is '1.48'

      The Average Number of Countries on 'Prime Video' is '1.27'

      The Average Number of Countries on 'Disney+' is '1.37'


print(f'''
      Accross All Platforms Total Count of Country is '{df_movies_count_countries['Number of Countries'].max()}'\n
      Total Count of Country on 'Netflix' is '{netflix_countries_movies['Number of Countries'].max()}'\n
      Total Count of Country on 'Hulu' is '{hulu_countries_movies['Number of Countries'].max()}'\n
      Total Count of Country on 'Prime Video' is '{prime_video_countries_movies['Number of Countries'].max()}'\n
      Total Count of Country on 'Disney+' is '{disney_countries_movies['Number of Countries'].max()}'\n 
      ''')

      Accross All Platforms Total Count of Country is '27'

      Total Count of Country on 'Netflix' is '10'

      Total Count of Country on 'Hulu' is '10'

      Total Count of Country on 'Prime Video' is '27'

      Total Count of Country on 'Disney+' is '15'


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_movies_count_countries['Number of Countries'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_movies_count_countries['Number of Countries'], ax = ax[1])
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Number of Countries s Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_countries_movies['Number of Countries'], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_countries_movies['Number of Countries'], color = 'red', legend = True, kde = True)
sns.histplot(hulu_countries_movies['Number of Countries'], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_countries_movies['Number of Countries'], color = 'darkblue', legend = True, kde = True) 
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


df_lan = df_movies_country['Country'].str.split(',').apply(pd.Series).stack()
del df_movies_country['Country']
df_lan.index = df_lan.index.droplevel(-1)
df_lan.name = 'Country'
df_movies_country = df_movies_country.join(df_lan)
df_movies_country.drop_duplicates(inplace = True)


df_movies_country.head(5)


country_count = df_movies_country.groupby('Country')['Title'].count()
country_movies = df_movies_country.groupby('Country')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
country_data_movies = pd.concat([country_count, country_movies], axis = 1).reset_index().rename(columns = {'Title' : 'Movies Count'})
country_data_movies = country_data_movies.sort_values(by = 'Movies Count', ascending = False)


# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_country_movies = country_data_movies[country_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_country_movies = netflix_country_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

hulu_country_movies = country_data_movies[country_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_country_movies = hulu_country_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

prime_video_country_movies = country_data_movies[country_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_country_movies = prime_video_country_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)

disney_country_movies = country_data_movies[country_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_country_movies = disney_country_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)


# Country with Movies Counts - All Platforms Combined
country_data_movies.sort_values(by = 'Movies Count', ascending = False)[:10]


fig = px.bar(x = country_data_movies['Country'][:50],
             y = country_data_movies['Movies Count'][:50], 
             color = country_data_movies['Movies Count'][:50],
             color_continuous_scale = 'Teal_r', 
             labels = { 'x' : 'Country', 'y' : 'Movies Count'},
             title  = 'Major Countries : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.choropleth(data_frame = country_data_movies, locations = 'Country', locationmode = 'country names', color = 'Movies Count', color_continuous_scale = 'deep')

fig.show()


df_country_high_movies = country_data_movies.sort_values(by = 'Movies Count', ascending = False).reset_index()
df_country_high_movies = df_country_high_movies.drop(['index'], axis = 1)
# filter = (country_data_movies['Movies Count'] == (country_data_movies['Movies Count'].max()))
# df_country_high_movies = country_data_movies[filter]
 
# highest_rated_movies = country_data_movies.loc[country_data_movies['Movies Count'].idxmax()]
 
print('\nCountry with Highest Ever Movies Count are : All Platforms Combined\n')
df_country_high_movies.head(5)

Country with Highest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_country_high_movies['Country'][:15],
             x = df_country_high_movies['Movies Count'][:15], 
             color = df_country_high_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Country', 'x' : 'Movies Count'},
             title  = 'Country with Highest Movies : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_country_low_movies = country_data_movies.sort_values(by = 'Movies Count', ascending = True).reset_index()
df_country_low_movies = df_country_low_movies.drop(['index'], axis = 1)
# filter = (country_data_movies['Movies Count'] == (country_data_movies['Movies Count'].min()))
# df_country_low_movies = country_data_movies[filter]

print('\nCountry with Lowest Ever Movies Count are : All Platforms Combined\n')
df_country_low_movies.head(5)

Country with Lowest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_country_low_movies['Country'][:15],
             x = df_country_low_movies['Movies Count'][:15], 
             color = df_country_low_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Country', 'x' : 'Movies Count'},
             title  = 'Country with Lowest Movies Count : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{country_data_movies['Country'].unique().shape[0]}' unique Country Count s were Given, They were Like this,\n
      
      {country_data_movies.sort_values(by = 'Movies Count', ascending = False)['Country'].unique()[:5]}\n
 
      The Highest Ever Movies Count Ever Any Movie Got is '{df_country_high_movies['Country'][0]}' : '{df_country_high_movies['Movies Count'].max()}'\n
 
      The Lowest Ever Movies Count Ever Any Movie Got is '{df_country_low_movies['Country'][0]}' : '{df_country_low_movies['Movies Count'].min()}'\n
      ''')

      Total '169' unique Country Count s were Given, They were Like this,

      
      ['United States' 'United Kingdom' 'Canada' 'India' 'France']

 
      The Highest Ever Movies Count Ever Any Movie Got is 'United States' : '10771'

 
      The Lowest Ever Movies Count Ever Any Movie Got is 'Macao' : '1'


fig = px.pie(country_data_movies[:10], names = 'Country', values = 'Movies Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'Movies Count based on Country')
fig.show()


# netflix_country_movies = country_data_movies[country_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_country_movies = netflix_country_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
netflix_country_high_movies = df_country_high_movies.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_country_high_movies = netflix_country_high_movies.drop(['index'], axis = 1)
 
netflix_country_low_movies = df_country_high_movies.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_country_low_movies = netflix_country_low_movies.drop(['index'], axis = 1)
 
netflix_country_high_movies.head(5)


fig = px.bar(x = netflix_country_high_movies['Country'][:15],
             y = netflix_country_high_movies['Netflix'][:15], 
             color = netflix_country_high_movies['Netflix'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Country', 'x' : 'Movies Count'},
             title  = 'Country with Highest Movies : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.choropleth(data_frame = netflix_country_movies, locations = 'Country', locationmode = 'country names', color = 'Netflix', color_continuous_scale = 'Reds')

fig.show()


# hulu_country_movies = country_data_movies[country_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_country_movies = hulu_country_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
hulu_country_high_movies = df_country_high_movies.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_country_high_movies = hulu_country_high_movies.drop(['index'], axis = 1)
 
hulu_country_low_movies = df_country_high_movies.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_country_low_movies = hulu_country_low_movies.drop(['index'], axis = 1)
 
hulu_country_high_movies.head(5)


fig = px.bar(x = hulu_country_high_movies['Country'][:15],
             y = hulu_country_high_movies['Hulu'][:15], 
             color = hulu_country_high_movies['Hulu'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Country', 'x' : 'Movies Count'},
             title  = 'Country with Highest Movies : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.choropleth(data_frame = hulu_country_movies, locations = 'Country', locationmode = 'country names', color = 'Hulu', color_continuous_scale = 'Greens')

fig.show()


# prime_video_country_movies = country_data_movies[country_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_country_movies = prime_video_country_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)
 
prime_video_country_high_movies = df_country_high_movies.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_country_high_movies = prime_video_country_high_movies.drop(['index'], axis = 1)
 
prime_video_country_low_movies = df_country_high_movies.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_country_low_movies = prime_video_country_low_movies.drop(['index'], axis = 1)
 
prime_video_country_high_movies.head(5)


fig = px.bar(x = prime_video_country_high_movies['Country'][:15],
             y = prime_video_country_high_movies['Prime Video'][:15], 
             color = prime_video_country_high_movies['Prime Video'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Country', 'x' : 'Movies Count'},
             title  = 'Country with Highest Movies : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.choropleth(data_frame = prime_video_country_movies, locations = 'Country', locationmode = 'country names', color = 'Prime Video', color_continuous_scale = 'Blues')

fig.show()


# disney_country_movies = country_data_movies[country_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_country_movies = disney_country_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)
 
disney_country_high_movies = df_country_high_movies.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_country_high_movies = disney_country_high_movies.drop(['index'], axis = 1)
 
disney_country_low_movies = df_country_high_movies.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_country_low_movies = disney_country_low_movies.drop(['index'], axis = 1)
 
disney_country_high_movies.head(5)


fig = px.bar(x = disney_country_high_movies['Country'][:15],
             y = disney_country_high_movies['Disney+'][:15], 
             color = disney_country_high_movies['Disney+'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Country', 'x' : 'Movies Count'},
             title  = 'Country with Highest Movies : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.choropleth(data_frame = disney_country_movies, locations = 'Country', locationmode = 'country names', color = 'Disney+', color_continuous_scale = 'BuPu')

fig.show()


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(country_data_movies['Movies Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(country_data_movies['Movies Count'], ax = ax[1])
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Country Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(disney_country_movies['Disney+'][:50], color = 'darkblue', legend = True, kde = True)  
sns.histplot(prime_video_country_movies['Prime Video'][:50], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_country_movies['Netflix'][:50], color = 'red', legend = True, kde = True)
sns.histplot(hulu_country_movies['Hulu'][:50], color = 'lightgreen', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Disney+', 'Prime Video', 'Netflix', 'Hulu'])
plt.show()


print(f'''
      The Country with Highest Movies Count Ever Got is '{df_country_high_movies['Country'][0]}' : '{df_country_high_movies['Movies Count'].max()}'\n
      The Country with Lowest Movies Count Ever Got is '{df_country_low_movies['Country'][0]}' : '{df_country_low_movies['Movies Count'].min()}'\n
      
      The Country with Highest Movies Count on 'Netflix' is '{netflix_country_high_movies['Country'][0]}' : '{netflix_country_high_movies['Netflix'].max()}'\n
      The Country with Lowest Movies Count on 'Netflix' is '{netflix_country_low_movies['Country'][0]}' : '{netflix_country_low_movies['Netflix'].min()}'\n
      
      The Country with Highest Movies Count on 'Hulu' is '{hulu_country_high_movies['Country'][0]}' : '{hulu_country_high_movies['Hulu'].max()}'\n
      The Country with Lowest Movies Count on 'Hulu' is '{hulu_country_low_movies['Country'][0]}' : '{hulu_country_low_movies['Hulu'].min()}'\n
      
      The Country with Highest Movies Count on 'Prime Video' is '{prime_video_country_high_movies['Country'][0]}' : '{prime_video_country_high_movies['Prime Video'].max()}'\n
      The Country with Lowest Movies Count on 'Prime Video' is '{prime_video_country_low_movies['Country'][0]}' : '{prime_video_country_low_movies['Prime Video'].min()}'\n
      
      The Country with Highest Movies Count on 'Disney+' is '{disney_country_high_movies['Country'][0]}' : '{disney_country_high_movies['Disney+'].max()}'\n
      The Country with Lowest Movies Count on 'Disney+' is '{disney_country_low_movies['Country'][0]}' : '{disney_country_low_movies['Disney+'].min()}'\n 
      ''')

      The Country with Highest Movies Count Ever Got is 'United States' : '10771'

      The Country with Lowest Movies Count Ever Got is 'Macao' : '1'

      
      The Country with Highest Movies Count on 'Netflix' is 'United States' : '1800'

      The Country with Lowest Movies Count on 'Netflix' is 'Macao' : '0'

      
      The Country with Highest Movies Count on 'Hulu' is 'United States' : '790'

      The Country with Lowest Movies Count on 'Hulu' is 'Macao' : '0'

      
      The Country with Highest Movies Count on 'Prime Video' is 'United States' : '8040'

      The Country with Lowest Movies Count on 'Prime Video' is 'Federal Republic of Yugoslavia' : '0'

      
      The Country with Highest Movies Count on 'Disney+' is 'United States' : '546'

      The Country with Lowest Movies Count on 'Disney+' is 'Albania' : '0'


# Distribution of movies country in each platform
plt.figure(figsize = (20, 5))
plt.title('Country with Movies Count for All Platforms')
sns.violinplot(x = country_data_movies['Movies Count'][:100], color = 'gold', legend = True, kde = True, shade = False)
plt.show()


# Distribution of Country Movies Count in each platform
f1, ax1 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = netflix_country_movies['Netflix'][:100], color = 'red', ax = ax1[0])
sns.violinplot(x = hulu_country_movies['Hulu'][:100], color = 'lightgreen', ax = ax1[1])
 
f2, ax2 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = prime_video_country_movies['Prime Video'][:100], color = 'lightblue', ax = ax2[0])
sns.violinplot(x = disney_country_movies['Disney+'][:100], color = 'darkblue', ax = ax2[1])
plt.show()


print(f'''
      Accross All Platforms the Average Movies Count of Country is '{round(country_data_movies['Movies Count'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Country on 'Netflix' is '{round(netflix_country_movies['Netflix'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Country on 'Hulu' is '{round(hulu_country_movies['Hulu'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Country on 'Prime Video' is '{round(prime_video_country_movies['Prime Video'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Country on 'Disney+' is '{round(disney_country_movies['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Movies Count of Country is '127.17'

      The Average Movies Count of Country on 'Netflix' is '45.85'

      The Average Movies Count of Country on 'Hulu' is '23.56'

      The Average Movies Count of Country on 'Prime Video' is '94.19'

      The Average Movies Count of Country on 'Disney+' is '17.41'


print(f'''
      Accross All Platforms Total Count of Country is '{country_data_movies['Country'].unique().shape[0]}'\n
      Total Count of Country on 'Netflix' is '{netflix_country_movies['Country'].unique().shape[0]}'\n
      Total Count of Country on 'Hulu' is '{hulu_country_movies['Country'].unique().shape[0]}'\n
      Total Count of Country on 'Prime Video' is '{prime_video_country_movies['Country'].unique().shape[0]}'\n
      Total Count of Country on 'Disney+' is '{disney_country_movies['Country'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Country is '169'

      Total Count of Country on 'Netflix' is '102'

      Total Count of Country on 'Hulu' is '66'

      Total Count of Country on 'Prime Video' is '163'

      Total Count of Country on 'Disney+' is '44'


plt.figure(figsize = (20, 5))
sns.lineplot(x = country_data_movies['Country'][:10], y = country_data_movies['Netflix'][:10], color = 'red')
sns.lineplot(x = country_data_movies['Country'][:10], y = country_data_movies['Hulu'][:10], color = 'lightgreen')
sns.lineplot(x = country_data_movies['Country'][:10], y = country_data_movies['Prime Video'][:10], color = 'lightblue')
sns.lineplot(x = country_data_movies['Country'][:10], y = country_data_movies['Disney+'][:10], color = 'darkblue')
plt.xlabel('Country', fontsize = 20)
plt.ylabel('Movies Count', fontsize = 20)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_co_ax1 = sns.lineplot(y = country_data_movies['Country'][:10], x = country_data_movies['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_co_ax2 = sns.lineplot(y = country_data_movies['Country'][:10], x = country_data_movies['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_co_ax3 = sns.lineplot(y = country_data_movies['Country'][:10], x = country_data_movies['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_co_ax4 = sns.lineplot(y = country_data_movies['Country'][:10], x = country_data_movies['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_co_ax1.title.set_text(labels[0])
h_co_ax2.title.set_text(labels[1])
p_co_ax3.title.set_text(labels[2])
d_co_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_co_ax1 = sns.barplot(y = netflix_country_movies['Country'][:10], x = netflix_country_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_co_ax2 = sns.barplot(y = hulu_country_movies['Country'][:10], x = hulu_country_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_co_ax3 = sns.barplot(y = prime_video_country_movies['Country'][:10], x = prime_video_country_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_co_ax4 = sns.barplot(y = disney_country_movies['Country'][:10], x = disney_country_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_co_ax1.title.set_text(labels[0])
h_co_ax2.title.set_text(labels[1])
p_co_ax3.title.set_text(labels[2])
d_co_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Country  Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_country_movies['Netflix'][:10], color = 'red', legend = True)
sns.kdeplot(hulu_country_movies['Hulu'][:10], color = 'green', legend = True)
sns.kdeplot(prime_video_country_movies['Prime Video'][:10], color = 'lightblue', legend = True)
sns.kdeplot(disney_country_movies['Disney+'][:10], color = 'darkblue', legend = True)                                      
                                      
# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_co_ax1 = sns.barplot(y = country_data_movies['Country'][:10], x = country_data_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_co_ax2 = sns.barplot(y = country_data_movies['Country'][:10], x = country_data_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_co_ax3 = sns.barplot(y = country_data_movies['Country'][:10], x = country_data_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_co_ax4 = sns.barplot(y = country_data_movies['Country'][:10], x = country_data_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_co_ax1.title.set_text(labels[0])
h_co_ax2.title.set_text(labels[1])
p_co_ax3.title.set_text(labels[2])
d_co_ax4.title.set_text(labels[3])
 
plt.show()


df_movies_mixed_countries.drop(df_movies_mixed_countries.loc[df_movies_mixed_countries['Country'] == "NA"].index, inplace = True)
# df_movies_mixed_countries = df_movies_mixed_countries[df_movies_mixed_countries.Country != "NA"]
df_movies_mixed_countries.drop(df_movies_mixed_countries.loc[df_movies_mixed_countries['Number of Countries'] == 1].index, inplace = True)


df_movies_mixed_countries.head(5)


mixed_countries_count = df_movies_mixed_countries.groupby('Country')['Title'].count()
mixed_countries_movies = df_movies_mixed_countries.groupby('Country')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
mixed_countries_data_movies = pd.concat([mixed_countries_count, mixed_countries_movies], axis = 1).reset_index().rename(columns = {'Title' : 'Movies Count', 'Country' : 'Mixed Country'})
mixed_countries_data_movies = mixed_countries_data_movies.sort_values(by = 'Movies Count', ascending = False)


mixed_countries_data_movies.head(5)


# Mixed Country with Movies Counts - All Platforms Combined
mixed_countries_data_movies.sort_values(by = 'Movies Count', ascending = False)[:10]


df_mixed_countries_high_movies = mixed_countries_data_movies.sort_values(by = 'Movies Count', ascending = False).reset_index()
df_mixed_countries_high_movies = df_mixed_countries_high_movies.drop(['index'], axis = 1)
# filter = (mixed_countries_data_movies['Movies Count'] = =  (mixed_countries_data_movies['Movies Count'].max()))
# df_mixed_countries_high_movies = mixed_countries_data_movies[filter]
 
# highest_rated_movies = mixed_countries_data_movies.loc[mixed_countries_data_movies['Movies Count'].idxmax()]
 
print('\nMixed Country with Highest Ever Movies Count are : All Platforms Combined\n')
df_mixed_countries_high_movies.head(5)

Mixed Country with Highest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_mixed_countries_high_movies['Mixed Country'][:15],
             x = df_mixed_countries_high_movies['Movies Count'][:15], 
             color = df_mixed_countries_high_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Mixed Country'},
             title  = 'Movies with Highest Number of Mixed Countries : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_mixed_countries_low_movies = mixed_countries_data_movies.sort_values(by = 'Movies Count', ascending = True).reset_index()
df_mixed_countries_low_movies = df_mixed_countries_low_movies.drop(['index'], axis = 1)
# filter = (mixed_countries_data_movies['Movies Count'] = =  (mixed_countries_data_movies['Movies Count'].min()))
# df_mixed_countries_low_movies = mixed_countries_data_movies[filter]
 
print('\nMixed Country with Lowest Ever Movies Count are : All Platforms Combined\n')
df_mixed_countries_low_movies.head(5)

Mixed Country with Lowest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_mixed_countries_low_movies['Mixed Country'][:15],
             x = df_mixed_countries_low_movies['Movies Count'][:15], 
             color = df_mixed_countries_low_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Mixed Country'},
             title  = 'Movies with Lowest Number of Mixed Countries : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_movies_countries['Country'].count()}' Titles are available on All Platforms, out of which\n
      You Can Choose to see Movies from Total '{mixed_countries_data_movies['Mixed Country'].unique().shape[0]}' Mixed Country, They were Like this, \n
 
      {mixed_countries_data_movies.sort_values(by = 'Movies Count', ascending = False)['Mixed Country'].head(5).unique()} etc. \n
 
      The Mixed Country with Highest Movies Count have '{mixed_countries_data_movies['Movies Count'].max()}' Movies Available is '{df_mixed_countries_high_movies['Mixed Country'][0]}', &\n
      The Mixed Country with Lowest Movies Count have '{mixed_countries_data_movies['Movies Count'].min()}' Movies Available is '{df_mixed_countries_low_movies['Mixed Country'][0]}'
      ''')

      Total '16620' Titles are available on All Platforms, out of which

      You Can Choose to see Movies from Total '1279' Mixed Country, They were Like this, 

 
      ['United Kingdom,United States' 'United States,Canada'
 'Canada,United States' 'United States,United Kingdom'
 'United States,Mexico'] etc. 

 
      The Mixed Country with Highest Movies Count have '182' Movies Available is 'United Kingdom,United States', &

      The Mixed Country with Lowest Movies Count have '1' Movies Available is 'United Kingdom,Sweden,Cayman Islands'


fig = px.pie(mixed_countries_data_movies[:10], names = 'Mixed Country', values = 'Movies Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'Movies Count based on Mixed Country')
fig.show()


# netflix_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_mixed_countries_movies = netflix_mixed_countries_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
netflix_mixed_countries_high_movies = df_mixed_countries_high_movies.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_countries_high_movies = netflix_mixed_countries_high_movies.drop(['index'], axis = 1)
 
netflix_mixed_countries_low_movies = df_mixed_countries_high_movies.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_mixed_countries_low_movies = netflix_mixed_countries_low_movies.drop(['index'], axis = 1)
 
netflix_mixed_countries_high_movies.head(5)


# hulu_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_mixed_countries_movies = hulu_mixed_countries_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
hulu_mixed_countries_high_movies = df_mixed_countries_high_movies.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_countries_high_movies = hulu_mixed_countries_high_movies.drop(['index'], axis = 1)
 
hulu_mixed_countries_low_movies = df_mixed_countries_high_movies.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_mixed_countries_low_movies = hulu_mixed_countries_low_movies.drop(['index'], axis = 1)
 
hulu_mixed_countries_high_movies.head(5)


# prime_video_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_mixed_countries_movies = prime_video_mixed_countries_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)
 
prime_video_mixed_countries_high_movies = df_mixed_countries_high_movies.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_countries_high_movies = prime_video_mixed_countries_high_movies.drop(['index'], axis = 1)
 
prime_video_mixed_countries_low_movies = df_mixed_countries_high_movies.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_mixed_countries_low_movies = prime_video_mixed_countries_low_movies.drop(['index'], axis = 1)
 
prime_video_mixed_countries_high_movies.head(5)


# disney_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_mixed_countries_movies = disney_mixed_countries_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)
 
disney_mixed_countries_high_movies = df_mixed_countries_high_movies.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_countries_high_movies = disney_mixed_countries_high_movies.drop(['index'], axis = 1)
 
disney_mixed_countries_low_movies = df_mixed_countries_high_movies.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_mixed_countries_low_movies = disney_mixed_countries_low_movies.drop(['index'], axis = 1)
 
disney_mixed_countries_high_movies.head(5)


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(mixed_countries_data_movies['Movies Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(mixed_countries_data_movies['Movies Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_countries_movies = netflix_mixed_countries_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

hulu_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_countries_movies = hulu_mixed_countries_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

prime_video_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_countries_movies = prime_video_mixed_countries_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)

disney_mixed_countries_movies = mixed_countries_data_movies[mixed_countries_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_countries_movies = disney_mixed_countries_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Country Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(prime_video_mixed_countries_movies['Prime Video'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_mixed_countries_movies['Netflix'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_mixed_countries_movies['Hulu'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_mixed_countries_movies['Disney+'][:100], color = 'darkblue', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


print(f'''
      The Mixed Country with Highest Movies Count Ever Got is '{df_mixed_countries_high_movies['Mixed Country'][0]}' : '{df_mixed_countries_high_movies['Movies Count'].max()}'\n
      The Mixed Country with Lowest Movies Count Ever Got is '{df_mixed_countries_low_movies['Mixed Country'][0]}' : '{df_mixed_countries_low_movies['Movies Count'].min()}'\n
      
      The Mixed Country with Highest Movies Count on 'Netflix' is '{netflix_mixed_countries_high_movies['Mixed Country'][0]}' : '{netflix_mixed_countries_high_movies['Netflix'].max()}'\n
      The Mixed Country with Lowest Movies Count on 'Netflix' is '{netflix_mixed_countries_low_movies['Mixed Country'][0]}' : '{netflix_mixed_countries_low_movies['Netflix'].min()}'\n
      
      The Mixed Country with Highest Movies Count on 'Hulu' is '{hulu_mixed_countries_high_movies['Mixed Country'][0]}' : '{hulu_mixed_countries_high_movies['Hulu'].max()}'\n
      The Mixed Country with Lowest Movies Count on 'Hulu' is '{hulu_mixed_countries_low_movies['Mixed Country'][0]}' : '{hulu_mixed_countries_low_movies['Hulu'].min()}'\n
      
      The Mixed Country with Highest Movies Count on 'Prime Video' is '{prime_video_mixed_countries_high_movies['Mixed Country'][0]}' : '{prime_video_mixed_countries_high_movies['Prime Video'].max()}'\n
      The Mixed Country with Lowest Movies Count on 'Prime Video' is '{prime_video_mixed_countries_low_movies['Mixed Country'][0]}' : '{prime_video_mixed_countries_low_movies['Prime Video'].min()}'\n
      
      The Mixed Country with Highest Movies Count on 'Disney+' is '{disney_mixed_countries_high_movies['Mixed Country'][0]}' : '{disney_mixed_countries_high_movies['Disney+'].max()}'\n
      The Mixed Country with Lowest Movies Count on 'Disney+' is '{disney_mixed_countries_low_movies['Mixed Country'][0]}' : '{disney_mixed_countries_low_movies['Disney+'].min()}'\n 
      ''')

      The Mixed Country with Highest Movies Count Ever Got is 'United Kingdom,United States' : '182'

      The Mixed Country with Lowest Movies Count Ever Got is 'United Kingdom,Sweden,Cayman Islands' : '1'

      
      The Mixed Country with Highest Movies Count on 'Netflix' is 'United Kingdom,United States' : '43'

      The Mixed Country with Lowest Movies Count on 'Netflix' is 'Israel,Switzerland,Germany,France' : '0'

      
      The Mixed Country with Highest Movies Count on 'Hulu' is 'United States,Canada' : '21'

      The Mixed Country with Lowest Movies Count on 'Hulu' is 'Israel,Switzerland,Germany,France' : '0'

      
      The Mixed Country with Highest Movies Count on 'Prime Video' is 'United Kingdom,United States' : '120'

      The Mixed Country with Lowest Movies Count on 'Prime Video' is 'Lebanon,Qatar' : '0'

      
      The Mixed Country with Highest Movies Count on 'Disney+' is 'United States,United Kingdom' : '16'

      The Mixed Country with Lowest Movies Count on 'Disney+' is 'Israel,Switzerland,Germany,France' : '0'


print(f'''
      Accross All Platforms the Average Movies Count of Mixed Country is '{round(mixed_countries_data_movies['Movies Count'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Country on 'Netflix' is '{round(netflix_mixed_countries_movies['Netflix'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Country on 'Hulu' is '{round(hulu_mixed_countries_movies['Hulu'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Country on 'Prime Video' is '{round(prime_video_mixed_countries_movies['Prime Video'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Country on 'Disney+' is '{round(disney_mixed_countries_movies['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Movies Count of Mixed Country is '2.4'

      The Average Movies Count of Mixed Country on 'Netflix' is '1.77'

      The Average Movies Count of Mixed Country on 'Hulu' is '1.67'

      The Average Movies Count of Mixed Country on 'Prime Video' is '2.21'

      The Average Movies Count of Mixed Country on 'Disney+' is '2.46'


print(f'''
      Accross All Platforms Total Count of Mixed Country is '{mixed_countries_data_movies['Mixed Country'].unique().shape[0]}'\n
      Total Count of Mixed Country on 'Netflix' is '{netflix_mixed_countries_movies['Mixed Country'].unique().shape[0]}'\n
      Total Count of Mixed Country on 'Hulu' is '{hulu_mixed_countries_movies['Mixed Country'].unique().shape[0]}'\n
      Total Count of Mixed Country on 'Prime Video' is '{prime_video_mixed_countries_movies['Mixed Country'].unique().shape[0]}'\n
      Total Count of Mixed Country on 'Disney+' is '{disney_mixed_countries_movies['Mixed Country'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Mixed Country is '1279'

      Total Count of Mixed Country on 'Netflix' is '399'

      Total Count of Mixed Country on 'Hulu' is '175'

      Total Count of Mixed Country on 'Prime Video' is '943'

      Total Count of Mixed Country on 'Disney+' is '52'


plt.figure(figsize = (20, 5))
sns.lineplot(x = mixed_countries_data_movies['Mixed Country'][:5], y = mixed_countries_data_movies['Netflix'][:5], color = 'red')
sns.lineplot(x = mixed_countries_data_movies['Mixed Country'][:5], y = mixed_countries_data_movies['Hulu'][:5], color = 'lightgreen')
sns.lineplot(x = mixed_countries_data_movies['Mixed Country'][:5], y = mixed_countries_data_movies['Prime Video'][:5], color = 'lightblue')
sns.lineplot(x = mixed_countries_data_movies['Mixed Country'][:5], y = mixed_countries_data_movies['Disney+'][:5], color = 'darkblue')
plt.xlabel('Mixed Country', fontsize = 15)
plt.ylabel('Movies Count', fontsize = 15)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_co_ax1 = sns.barplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_co_ax2 = sns.barplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_co_ax3 = sns.barplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_co_ax4 = sns.barplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_co_ax1.title.set_text(labels[0])
h_co_ax2.title.set_text(labels[1])
p_co_ax3.title.set_text(labels[2])
d_co_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_mco_ax1 = sns.lineplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_mco_ax2 = sns.lineplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_mco_ax3 = sns.lineplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_mco_ax4 = sns.lineplot(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_mco_ax1.title.set_text(labels[0])
h_mco_ax2.title.set_text(labels[1])
p_mco_ax3.title.set_text(labels[2])
d_mco_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Country  Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_mixed_countries_movies['Netflix'][:50], color = 'red', legend = True)
sns.kdeplot(hulu_mixed_countries_movies['Hulu'][:50], color = 'green', legend = True)
sns.kdeplot(prime_video_mixed_countries_movies['Prime Video'][:50], color = 'lightblue', legend = True)
sns.kdeplot(disney_mixed_countries_movies['Disney+'][:50], color = 'darkblue', legend = True)                                      

# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_mco_ax1 = sns.barplot(y = netflix_mixed_countries_movies['Mixed Country'][:10], x = netflix_mixed_countries_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_mco_ax2 = sns.barplot(y = hulu_mixed_countries_movies['Mixed Country'][:10], x = hulu_mixed_countries_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_mco_ax3 = sns.barplot(y = prime_video_mixed_countries_movies['Mixed Country'][:10], x = prime_video_mixed_countries_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_mco_ax4 = sns.barplot(y = disney_mixed_countries_movies['Mixed Country'][:10], x = disney_mixed_countries_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_mco_ax1.title.set_text(labels[0])
h_mco_ax2.title.set_text(labels[1])
p_mco_ax3.title.set_text(labels[2])
d_mco_ax4.title.set_text(labels[3])
 
plt.show()


fig = go.Figure(go.Funnel(y = mixed_countries_data_movies['Mixed Country'][:10], x = mixed_countries_data_movies['Movies Count'][:10]))
fig.show()

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	Language	Plotline	Runtime	Kind	Seasons	Netflix	Prime Video
0	1	Inception	2010	13+	8.8	87%	Christopher Nolan	Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ...	Action,Adventure,Sci-Fi,Thriller	United States,United Kingdom	English,Japanese,French	Dom Cobb is a skilled thief, the absolute best...	148.0	movie	NaN	1	0
1	2	The Matrix	1999	16+	8.7	88%	Lana Wachowski,Lilly Wachowski	Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo...	Action,Sci-Fi	United States	English	Thomas A. Anderson is a man living two lives. ...	136.0	movie	NaN	1	0
2	3	Avengers: Infinity War	2018	13+	8.4	85%	Anthony Russo,Joe Russo	Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo...	Action,Adventure,Sci-Fi	United States	English	As the Avengers and their allies have continue...	149.0	movie	NaN	1	0
3	4	Back to the Future	1985	7+	8.5	96%	Robert Zemeckis	Michael J. Fox,Christopher Lloyd,Lea Thompson,...	Adventure,Comedy,Sci-Fi	United States	English	Marty McFly, a typical American teenager of th...	116.0	movie	NaN	1	0
4	5	The Good, the Bad and the Ugly	1966	16+	8.8	97%	Sergio Leone	Eli Wallach,Clint Eastwood,Lee Van Cleef,Aldo ...	Western	Italy,Spain,West Germany,United States	Italian	Blondie (The Good) (Clint Eastwood) is a profe...	161.0	movie	NaN	1	1

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	Language	Plotline	Runtime	Kind	Netflix	Prime Video	Service Provider
0	1	Inception	2010	13	8.8	87	Christopher Nolan	Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ...	Action,Adventure,Sci-Fi,Thriller	United States,United Kingdom	English,Japanese,French	Dom Cobb is a skilled thief, the absolute best...	148	movie	1	0	Netflix
1	2	The Matrix	1999	16	8.7	88	Lana Wachowski,Lilly Wachowski	Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo...	Action,Sci-Fi	United States	English	Thomas A. Anderson is a man living two lives. ...	136	movie	1	0	Netflix
2	3	Avengers: Infinity War	2018	13	8.4	85	Anthony Russo,Joe Russo	Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo...	Action,Adventure,Sci-Fi	United States	English	As the Avengers and their allies have continue...	149	movie	1	0	Netflix
3	4	Back to the Future	1985	7	8.5	96	Robert Zemeckis	Michael J. Fox,Christopher Lloyd,Lea Thompson,...	Adventure,Comedy,Sci-Fi	United States	English	Marty McFly, a typical American teenager of th...	116	movie	1	0	Netflix
4	5	The Good, the Bad and the Ugly	1966	16	8.8	97	Sergio Leone	Eli Wallach,Clint Eastwood,Lee Van Cleef,Aldo ...	Western	Italy,Spain,West Germany,United States	Italian	Blondie (The Good) (Clint Eastwood) is a profe...	161	movie	1	1	Netflix

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
count	16923.000000	16923.000000	16923.000000	16923.000000	16923.000000	16923.000000	16923.0
mean	8462.000000	2003.211901	0.214915	0.062637	0.727235	0.033150	0.0
std	4885.393638	20.526532	0.410775	0.242315	0.445394	0.179034	0.0
min	1.000000	1901.000000	0.000000	0.000000	0.000000	0.000000	0.0
25%	4231.500000	2001.000000	0.000000	0.000000	0.000000	0.000000	0.0
50%	8462.000000	2012.000000	0.000000	0.000000	1.000000	0.000000	0.0
75%	12692.500000	2016.000000	0.000000	0.000000	1.000000	0.000000	0.0
max	16923.000000	2020.000000	1.000000	1.000000	1.000000	1.000000	0.0

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
ID	1.000000	-0.217816	-0.644470	-0.129926	0.469301	0.263530	NaN
Year	-0.217816	1.000000	0.256151	0.101337	-0.255578	-0.047258	NaN
Netflix	-0.644470	0.256151	1.000000	-0.118032	-0.745141	-0.089649	NaN
Hulu	-0.129926	0.101337	-0.118032	1.000000	-0.284654	-0.039693	NaN
Prime Video	0.469301	-0.255578	-0.745141	-0.284654	1.000000	-0.289008	NaN
Disney+	0.263530	-0.047258	-0.089649	-0.039693	-0.289008	1.000000	NaN
Type	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Language	Plotline	Runtime	Kind	Netflix	Service Provider	Country
0	1	Inception	2010	13	8.8	87	Christopher Nolan	Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ...	Action,Adventure,Sci-Fi,Thriller	English,Japanese,French	Dom Cobb is a skilled thief, the absolute best...	148	movie	1	Netflix	United States
0	1	Inception	2010	13	8.8	87	Christopher Nolan	Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ...	Action,Adventure,Sci-Fi,Thriller	English,Japanese,French	Dom Cobb is a skilled thief, the absolute best...	148	movie	1	Netflix	United Kingdom
1	2	The Matrix	1999	16	8.7	88	Lana Wachowski,Lilly Wachowski	Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo...	Action,Sci-Fi	English	Thomas A. Anderson is a man living two lives. ...	136	movie	1	Netflix	United States
2	3	Avengers: Infinity War	2018	13	8.4	85	Anthony Russo,Joe Russo	Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo...	Action,Adventure,Sci-Fi	English	As the Avengers and their allies have continue...	149	movie	1	Netflix	United States
3	4	Back to the Future	1985	7	8.5	96	Robert Zemeckis	Michael J. Fox,Christopher Lloyd,Lea Thompson,...	Adventure,Comedy,Sci-Fi	English	Marty McFly, a typical American teenager of th...	116	movie	1	Netflix	United States

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Prime Video	Disney+	Service Provider	Number of Countries
0	6906	Somewhere Else Tomorrow	2013	13	7.5	NA	Daniel Rintz	Issa Breibish,Kristian Bruun,Megan Gay,Grant J...	Documentary,Adventure,Drama,News	Germany,Canada,Vietnam,United Kingdom,Turkey,T...	...	Promising young student Chi-Hao is sent away t...	107	movie	1	0	Prime Video	27
1	6333	Poverty, Inc.	2014	NR	7.7	NA	Michael Matheson Miller	Robert Sirico	Documentary,History,News	United States,United Kingdom,Thailand,Swazilan...	...	The lady is Mrs. Hilyard, a wealthy poetess wh...	94	movie	1	0	Prime Video	20
2	4382	Samsara	2011	13	8.5	76	Ron Fricke	Balinese Tari Legong Dancers,Ni Made Megahadi ...	Documentary,Music	United States,Indonesia,Singapore,Thailand,Ken...	...	NA	102	movie	1	0	Prime Video	19
3	8004	Lost Kites	2016	NR	7	NA	Samuel Rich,Gabriella Fritz	NA	Documentary	United States,Belgium,Brazil,Cambodia,China,In...	...	All fourteen-year-old Robbie Hendrick ever wan...	50	movie	1	0	Prime Video	18
4	16012	Mulan II	2004	0	5.7	0	Darrell Rooney,Lynne Southerland	Ming-Na Wen,BD Wong,Mark Moseley,Lucy Liu,Harv...	Animation,Action,Comedy,Family,Musical	United States,South Korea,Singapore,Russia,Mal...	...	Tia and her brother Tony have supernatural pow...	79	movie	0	1	Disney+	15

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Prime Video	Service Provider	Number of Countries
0	8436	Citizen Architect: Samuel Mockbee and the Spir...	2010	NR	7.6	NA	Sam Wainwright Douglas	NA	Documentary,Biography,History	United States	...	Apollo 13 was supposed to be the third human s...	57	movie	1	Prime Video	1
1	10816	72 Hours: Martyr Who Never Died	2019	NR	5.2	NA	Avinash Dhyani	Avinash Dhyani,Yeshi Dema,Alka Amin,Virendra S...	Action,Biography,Drama,War	India	...	NA	130	movie	1	Prime Video	1
2	10817	Looking for Lenny	2011	13	6.2	NA	Elan Gale	Lenny Bruce,Richard Lewis,Robin Williams,Rosea...	Documentary	United States	...	Twenty years have passed since Dr. Vincent Edw...	65	movie	1	Prime Video	1
3	10818	Forest Fairies	2015	0	6.6	NA	Justin G. Dyck	Emily Agard,Lora Burke,Brian Scott Carleton,Wi...	Adventure,Family,Fantasy	Canada	...	Bank comptroller John Hewitt is a much-respect...	90	movie	1	Prime Video	1
4	10819	The Unwilling	2017	18	4.2	95	Jonathan Heap	David Lipper,Dina Meyer,Bree Williamson,Robert...	Horror,Thriller	United States	...	NA	84	movie	1	Prime Video	1

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Netflix	Service Provider	Number of Countries
0	287	A Shaun the Sheep Movie: Farmageddon	2019	0	6.8	96	Will Becher,Richard Phelan	Justin Fletcher,John Sparkes,Amalia Vitale,Kat...	Animation,Adventure,Comedy,Family,Fantasy,Sci-Fi	United Kingdom,France,Belgium,United States,Ch...	...	There is something strange going on in the pea...	86	movie	1	Netflix	10
1	2880	The Thief and the Fool	2013	NR	7.1	NA	Richard Williams	Vincent Price,Bobbi Page,Steve Lively,Ed E. Ca...	Animation,Action,Adventure,Comedy,Family,Fanta...	United Kingdom,United States,Canada,Taiwan,Ire...	...	When Tack upsets ZigZag the Vizier, the wizard...	90	movie	1	Netflix	9
2	781	Resident Evil: Afterlife	2010	16	6.3	22	Russell Mulcahy	Milla Jovovich,Oded Fehr,Ali Larter,Iain Glen,...	Action,Horror,Sci-Fi	France,Australia,Germany,United Kingdom,United...	...	Years after the Raccoon City disaster, Alice i...	94	movie	1	Netflix	8
3	554	Resident Evil: Extinction	2007	16	6.3	24	Russell Mulcahy	Milla Jovovich,Oded Fehr,Ali Larter,Iain Glen,...	Action,Horror,Sci-Fi	France,Australia,Germany,United Kingdom,United...	...	Years after the Raccoon City disaster, Alice i...	94	movie	1	Netflix	8
4	1644	Arctic Dogs	2019	7	4.7	13	Aaron Woodley	Jeremy Renner,Heidi Klum,James Franco,John Cle...	Animation,Adventure,Comedy,Family	India,United Kingdom,China,Canada,Japan,South ...	...	Swifty the Arctic Fox (Jeremy Renner) works in...	92	movie	1	Netflix	7

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Hulu	Prime Video	Service Provider	Number of Countries
0	3552	Monos	2019	16	6.9	92	Alejandro Landes	Sofia Buenaventura,Julián Giraldo,Karen Quinte...	Adventure,Drama,Thriller	Colombia,Argentina,Netherlands,Germany,Sweden,...	...	Teenage commandos perform military training ex...	102	movie	1	0	Hulu	10
1	3685	Manderlay	2005	NR	7.3	50	Lars von Trier	Bryce Dallas Howard,Isaach De Bankolé,Danny Gl...	Drama	Denmark,Sweden,Netherlands,France,Germany,Unit...	...	After gangster Mulligan's (Willem Dafoe's) car...	139	movie	1	0	Hulu	8
2	16432	Underground	2016	18	8.1	96	Emir Kusturica	Predrag 'Miki' Manojlovic,Lazar Ristovski,Mirj...	Comedy,Drama,Fantasy,War	Federal Republic of Yugoslavia,France,Germany,...	...	NA	170	movie	1	0	Hulu	8
3	16472	Curious George	2006	0	6.5	NA	Matthew O'Callaghan	Frank Welker,Will Ferrell,Shane Baumel,Timyra-...	Animation,Adventure,Comedy,Family	United States,Germany,Taiwan,France,Canada,Sou...	...	NA	87	movie	1	0	Hulu	8
4	3947	Sherlock Gnomes	2018	7	5.2	27	John Stevenson	Kelly Asbury,Mary J. Blige,Emily Blunt,Julio B...	Animation,Adventure,Comedy,Family,Fantasy,Myst...	United Kingdom,United States,India,Canada,Fran...	...	Sherlock Gnomes (Johnny Depp) and his assistan...	86	movie	1	1	Prime Video	6

	Country	Movies Count	Netflix	Hulu	Prime Video	Disney+
159	United States	10771	1800	790	8040	546
158	United Kingdom	1815	354	147	1331	61
26	Canada	1175	224	93	857	40
65	India	1143	569	9	659	4
52	France	791	188	83	537	16
54	Germany	527	125	44	380	5
72	Italy	450	58	18	386	1
8	Australia	342	65	24	244	21
138	Spain	333	125	24	195	1
74	Japan	305	95	45	168	7

	Country	Movies Count	Prime Video	Disney+
0	Macao	1	1	0
1	U.S. Virgin Islands	1	1	0
2	Botswana	1	0	1
3	Vanuatu	1	1	0
4	Bahrain	1	1	0

	Mixed Country	Movies Count	Netflix	Hulu	Prime Video	Disney+
970	United Kingdom,United States	182	43	18	120	13
1032	United States,Canada	160	36	21	102	14
162	Canada,United States	150	25	15	104	11
1225	United States,United Kingdom	104	19	17	61	16
1161	United States,Mexico	48	11	6	28	3

	Mixed Country	Movies Count	Netflix	Hulu	Prime Video
0	United Kingdom,Sweden,Cayman Islands	1	0	0	1
1	Canada,Yugoslavia	1	0	0	1
2	Chile,Argentina,Belgium	1	0	1	0
3	Chile,Argentina,France,Spain,United States	1	1	0	0
4	France,Estonia,Germany	1	0	0	1